© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94380
    Prev
    Next
    INDEX
    Explanations

    concepts related to public safety and health risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ottie
    -0.07
    ');?>"
    -0.06
    ç»ı
    -0.06
    oze
    -0.06
    dle
    -0.06
     èĸ
    -0.06
    (CharSequence
    -0.06
    IgnoreCase
    -0.06
    amaz
    -0.06
    vent
    -0.06
    POSITIVE LOGITS
    bbe
    0.08
    ous
    0.07
    usi
    0.06
    ntag
    0.06
    isode
    0.06
    IOD
    0.06
    /*/
    0.06
     Ñģи
    0.06
    wart
    0.06
    anto
    0.06
    Activations Density 0.070%

    No Known Activations